From 593e3ec151eef616cffc0ed4c099e20d542703bc Mon Sep 17 00:00:00 2001
From: bashonly <bashonly@protonmail.com>
Date: Mon, 9 Jun 2025 17:54:10 -0500
Subject: [PATCH] split into 2 methods, support Set and Map, add test data

Authored by: bashonly
---
 test/test_InfoExtractor.py | 14 +++++++++----
 yt_dlp/extractor/common.py | 42 +++++++++++++++++++++++---------------
 2 files changed, 35 insertions(+), 21 deletions(-)

diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py
index 52c1a6c943..9628c2927e 100644
--- a/test/test_InfoExtractor.py
+++ b/test/test_InfoExtractor.py
@@ -1952,7 +1952,7 @@ def test_search_nuxt_json(self):
             <script data-ssr="true" id="__NUXT_DATA__" type="application/json">
                 [
                     ["ShallowReactive",1],
-                    {"data":2,"state":21,"once":25},
+                    {"data":2,"state":21,"once":25,"_errors":28},
                     ["ShallowReactive",3],
                     {"$abcdef123456":4},
                     {"podcast":5,"activeEpisodeData":7},
@@ -1973,10 +1973,14 @@ def test_search_nuxt_json(self):
                     "Podcast Creator",
                     [],
                     {"$ssite-config":22},
-                    {"env":23,"name":24},
+                    {"env":23,"name":24,"map":26},
                     "production",
                     "podcast-website",
-                    ["Set"]
+                    ["Set"],
+                    ["Reactive",27],
+                    ["Map"],
+                    ["ShallowReactive",29],
+                    {}
                 ]
             </script>'''
         PAYLOAD = {
@@ -2003,9 +2007,11 @@ def test_search_nuxt_json(self):
                 '$ssite-config': {
                     'env': 'production',
                     'name': 'podcast-website',
+                    'map': {},
                 },
             },
-            'once': None,
+            'once': [],
+            '_errors': {},
         }
         BAD_HTML = '''
             <script data-ssr="true" id="__NUXT_DATA__" type="application/json">
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py
index 13593fe1f9..fe0b50770b 100644
--- a/yt_dlp/extractor/common.py
+++ b/yt_dlp/extractor/common.py
@@ -1795,29 +1795,21 @@ def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal
         ret = self._parse_json(js, video_id, transform_source=functools.partial(js_to_json, vars=args), fatal=fatal)
         return traverse_obj(ret, traverse) or {}
 
-    def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT):
-        """Parses metadata from Nuxt rich JSON payload arrays"""
+    def _resolve_nuxt_array(self, array, video_id, *, fatal=True, default=NO_DEFAULT):
+        """Resolves Nuxt rich JSON payload arrays"""
         # Ref: https://github.com/nuxt/nuxt/commit/9e503be0f2a24f4df72a3ccab2db4d3e63511f57
         #      https://github.com/nuxt/nuxt/pull/19205
-        IGNORED_TYPES = ('Map', 'Set', 'EmptyRef', 'EmptyShallowRef', 'NuxtError')
         ERROR_MSG = 'Unable to extract Nuxt JSON data'
 
-        if default is not NO_DEFAULT:
-            fatal = False
-
-        array = self._search_json(
-            r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage, 'Nuxt JSON data', video_id,
-            contains_pattern=r'\[(?s:.+)\]', default=NO_DEFAULT if fatal else [])
-
         result = [None]
         stack = [(result, 0, 0)]
         while stack:
             target, index, source = stack.pop()
             if 0 <= source < len(array):
                 element = array[source]
-            elif fatal:
-                raise ExtractorError(ERROR_MSG, video_id=video_id)
             elif default is NO_DEFAULT:
+                if fatal:
+                    raise ExtractorError(ERROR_MSG, video_id=video_id)
                 self.report_warning(ERROR_MSG, video_id=video_id)
                 return {}
             else:
@@ -1827,11 +1819,16 @@ def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT
                 if element[0] in ('ShallowReactive', 'Reactive', 'ShallowRef', 'Ref'):
                     stack.append((target, index, element[1]))
                     continue
-                if element[0] not in IGNORED_TYPES:
-                    self.write_debug(
-                        f'{video_id}: Discarding unsupported type in Nuxt payload: {element[0]}',
-                        only_once=True)
-                target[index] = None
+                if element[0] == 'Map':
+                    target[index] = {}
+                elif element[0] == 'Set':
+                    target[index] = []
+                else:
+                    target[index] = None
+                    if element[0] not in ('EmptyRef', 'EmptyShallowRef', 'NuxtError'):
+                        self.write_debug(
+                            f'{video_id}: Discarding unsupported type in Nuxt payload: {element[0]}',
+                            only_once=True)
                 continue
 
             if isinstance(element, list):
@@ -1850,6 +1847,17 @@ def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT
 
         return result[0]
 
+    def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT):
+        """Parses metadata from Nuxt rich JSON payloads embedded in HTML"""
+        if default is not NO_DEFAULT:
+            fatal = False
+
+        array = self._search_json(
+            r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage, 'Nuxt JSON data', video_id,
+            contains_pattern=r'\[(?s:.+)\]', default=NO_DEFAULT if fatal else [])
+
+        return self._resolve_nuxt_array(array, video_id, fatal=fatal, default=default)
+
     @staticmethod
     def _hidden_inputs(html):
         html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)